Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 50 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.6202. Min Act: -0.1700

Data Index: 820844 (Open Web Text)

Max Activating Token Index: 281

Text #1

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5518. Min Act: -0.1700

Data Index: 6127735 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5344. Min Act: -0.1700

Data Index: 6103306 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5249. Min Act: -0.1700

Data Index: 3947726 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5052. Min Act: -0.1700

Data Index: 7400387 (Open Web Text)

Max Activating Token Index: 410

Text #5

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4643. Min Act: -0.1700

Data Index: 4606727 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4828. Min Act: -0.1700

Data Index: 8013535 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4858. Min Act: -0.1700

Data Index: 2635435 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4715. Min Act: -0.1700

Data Index: 5981699 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4423. Min Act: -0.1700

Data Index: 185938 (Open Web Text)

Max Activating Token Index: 584

Text #10

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4511. Min Act: -0.1700

Data Index: 8096629 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4146. Min Act: -0.1700

Data Index: 6697874 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4557. Min Act: -0.1700

Data Index: 6197443 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4157. Min Act: -0.1700

Data Index: 7696439 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4175. Min Act: -0.1700

Data Index: 3418038 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4336. Min Act: -0.1700

Data Index: 5381323 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4302. Min Act: -0.1700

Data Index: 4874003 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4206. Min Act: -0.1700

Data Index: 2651075 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1245297 (Open Web Text)

Max Activating Token Index: 723

Text #19

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4050. Min Act: -0.1700

Data Index: 630630 (Open Web Text)

Max Activating Token Index: 185